© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130054
    Prev
    Next
    INDEX
    Explanations

    is/are followed by descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -1.12
    yors
    -1.12
    Thankfully
    -1.09
    itively
    -1.09
    我最
    -1.08
     المعرف
    -1.08
    ppio
    -1.07
    Conversely
    -1.06
     bVar
    -1.05
    ScopeManager
    -1.05
    POSITIVE LOGITS
    bandit
    1.25
     to
    1.18
     here
    1.17
    celtic
    1.16
     also
    1.16
     need
    1.14
    🩹
    1.08
    ukraine
    1.04
     together
    1.03
    nikon
    1.03
    Activations Density 0.086%

    No Known Activations